ai-gateway
Warn
Audited by Socket on May 11, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The stated purpose is plausible, but the key inconsistency is severe: a Vercel-branded gateway skill installs and relies on an unverified third-party CLI package not tied to Vercel’s documented tooling. Because that CLI receives the user’s AI Gateway API key and all prompt data, the skill presents a high supply-chain and credential-forwarding risk even though its user-facing function is coherent.
Confidence: 89%Severity: 86%
Audit Metadata